This is an R Markdown document to display the sampling locations of all used gutless oligochaetes for the diversity project along with their symbionts.
Code annotation was changed for readibility, code was not changed.
Current date: 13.05.2022
Status of the sample set: complete
Reason for this mapping: first project of PhD thesis
options(repos='http://cran.rstudio.com/')
#needed
#install.packages('seqinr')
#install.packages('plotly')
library(ggplot2)
library(plotly)
library(ggplot2)
library(maps)
library(mapdata)
library(seqinr)
library(tidyr)
library(reshape2)
##potential, delete unused later
#install.packages('maps')
#install.packages('tidyr')
#install.packages('mapproj')
#install.packages('viridis')
#install.packages('listviewer')
#install.packages('caTools')
#library(maps)
#library(sp)
#library(dplyr)
#library(stringr)
#library(mapproj)
#library(viridis)
#library(listviewer)
#library(caTools)
###Load sample data
Load metdadata table and symbiont table to be able to combine info later.
setwd("D:/Seafile/HomeOffice/alpha.all/worldmaps/")
mdata_raw <- read.table("metadata_gutless-oligochaetes.csv", sep = ";", header = T)
sdata <- read.fasta("all.16S.emirge.no-contamination.longerthan1000.fasta")
keep <- read.table("233_samples.txt", header = T)
mdata <- merge(keep, mdata_raw, by = "lib")
###colour schemes
colsymb=c("Alpha1"="#660000", "Alpha2"="#FF6633", "Alpha3"="#993300", "Alpha4"="#FF9999",
"Alpha5"="#CC3300", "Alpha6"="#FF9966", "Alpha7"="#CC0066", "Alpha8"="#FF0066",
"Alpha9"="#FF0033", "Alpha10"="#FF6600", "Alpha12"="#993333", "Alpha13"="#FF9900",
"Alpha14"="#FFCC99", "Alpha15"="#FF3333", "Alpha16"="#FF3300", "Delta1"="#6699FF",
"Delta2"="#CCFFFF", "Delta3"="#00FFFF", "Delta4"="#00CCFF", "Delta5"="#006699",
"Delta8"="#0000FF", "Delta11"="#669999","Delta12"="#0099CC", "Delta13"="#000066",
"Delta14"="#660099", "Gamma1"="#339933", "Gamma2"="#00FF00", "Gamma3"="#336633",
"Gamma4"="#99FF99", "Gamma4a"="#CCFFCC", "Gamma5"="#009966", "Gamma6"="#00FF99",
"Gamma7"="#999900", "Gamma8"="#CCCC99", "Spiro1"="#FF00FF", "Actinomarinales1"="#FFFF66",
"Marinimicrobia1"="#FFFF99")
world <- map_data("world")
###Plot sampling sites
sites <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
geom_point(data=mdata, aes(x=longitude, y=latitude, color=ocean), size=3)
#scale_size_continuous(range=c(1,12)) +
#theme_void()
plot(sites)
## Warning: Removed 6 rows containing missing values (geom_point).
ggplotly(sites)
##Merge symbiont and metadata
symbionts<-data.frame(names(sdata)) #get fasta headers
symsep<-separate(data = symbionts, col = names.sdata., into = c("lib", "symbiont"), sep = "\\.") # separate fasta header by lib and symbiont
msdata<-merge(mdata,symsep,by="lib") #merge symbiont and metadata
msdata$clade <- substr(msdata$symbiont, 0, 3)
##Plot symbionts
sloc <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
geom_point(data=msdata, aes(x=longitude, y=latitude, color=symbiont), size=3)
#scale_size_continuous(range=c(1,12)) +
#theme_void()
plot(sloc)
## Warning: Removed 23 rows containing missing values (geom_point).
ggplotly(sloc)
##Where are the symbionts?
#which symbionts to keep
#msdata <- msdata[grep("Alpha", msdata$symbiont), ] #choose symbiont clade to plot
Aloc <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , color = "grey", fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
#theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
geom_point(data=mdata, aes(x=longitude, y=latitude), size=3)+
geom_point(data=msdata, aes(x=longitude, y=latitude,color = symbiont), size=3)+
#geom_point(data=msdata, aes(x=longitude, y=latitude,color = symbiont), size=3, color ="#CC1F1B")+ #enable when all should have the same colour
scale_colour_manual(values=colsymb)
plot(Aloc)
## Warning: Removed 6 rows containing missing values (geom_point).
## Warning: Removed 23 rows containing missing values (geom_point).
ggplotly(Aloc)
loc <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , color = "grey", fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
#theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
geom_point(data=msdata, aes(x=longitude, y=latitude), size=2)+
geom_point(data=msdata, aes(x=longitude, y=latitude,color = symbiont), size=2)+
scale_colour_manual(values=colsymb) +
facet_wrap(~symbiont)
plot(loc)
ggplotly(loc)
##Where are the hosts?
hloc <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , color = "grey", fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
#theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
geom_point(data=mdata, aes(x=longitude, y=latitude), size=3)+
geom_point(data=mdata, aes(x=longitude, y=latitude, color = host_species), size=1, position = position_jitter(width = 3, height = 3))
plot(hloc)
## Warning: Removed 6 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing missing values (geom_point).
ggplotly(hloc)
hlocf <- ggplot() +
geom_polygon(data = world, aes(x=long, y = lat, group = group) , color = "grey", fill="grey")+
theme_bw() +
theme(panel.grid.major=element_blank(), panel.grid.minor=element_blank(),
panel.border=element_blank()) +
#theme(axis.title=element_blank(), axis.text=element_blank(), axis.ticks=element_blank())+
#geom_point(data=mdata, aes(x=longitude, y=latitude), size=3)+
geom_point(data=mdata, aes(x=longitude, y=latitude,color = host_species), size=3)+
facet_wrap(~host_species)
plot(hlocf)
#ggplotly(hlocf)
###What species do we have?
host1 <- ggplot(mdata, aes(fill=country, x=forcats::fct_infreq(host_species), group = country)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3, size = 6))
plot(host1)
#ggplotly(host)
host2 <- ggplot(mdata, aes(fill=host_species, x=forcats::fct_infreq(country), group = host_species)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3, size = 6))
plot(host2)
ggplotly(host2)
new_data<- unique(select(mdata,host_species,ocean, country))
host3 <- ggplot(new_data, aes(fill=host_species, x=forcats::fct_infreq(country))) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3, size = 6))
plot(host3)
ggplotly(host3)
###Where are our symbionts?
country <- ggplot(msdata, aes(fill=symbiont, forcats::fct_infreq(ocean), group = symbiont)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(country)
#ggplotly(country)
new_data<- unique(select(msdata,host_species,ocean, country,island_city, symbiont))
country2 <- ggplot(new_data, aes(fill=symbiont, forcats::fct_infreq(ocean), group = symbiont)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(country2)
#ggplotly(country)
new_data<- unique(select(msdata,host_species,ocean, country, island_city, symbiont))
island <- ggplot(new_data, aes(fill=symbiont, forcats::fct_infreq(country), group = symbiont)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(island)
#ggplotly(country)
country1 <- ggplot(msdata, aes(fill=symbiont, forcats::fct_infreq(country), group = symbiont)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(country1)
new_data<- unique(select(msdata,host_species, country, island_city, symbiont))
country <- ggplot(new_data, aes(fill=symbiont, forcats::fct_infreq(country), group = symbiont)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(country)
#ggplotly(country)
country <- ggplot(msdata, aes(fill=ocean, forcats::fct_infreq(symbiont), group = ocean)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))
plot(country)
#ggplotly(country)
new_data<- unique(select(msdata,host_species, country, island_city, symbiont))
sabu <- ggplot(new_data, aes(forcats::fct_infreq(symbiont),fill=factor(symbiont))) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))+
scale_fill_manual(values=colsymb)
plot(sabu)
#ggplotly(country)
country <- ggplot(msdata, aes(fill=country, forcats::fct_infreq(symbiont), group = country)) +
geom_bar(position="stack", stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))
plot(country)
#ggplotly(country)
countryh <- ggplot(mdata, aes(fill=host_species, forcats::fct_infreq(country), group = host_species)) +
geom_bar(stat="count")+
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.3))
plot(countryh)
#ggplotly(countryh)